List your company

Multi-task Reinforcement Learning on Meta-World MT10 v1 (Fixed)

88Success RateMT-MH-SAC
11.0431.025170.98Mar 30, 2020Mar 14, 2021Feb 26, 2022Feb 10, 2023Jan 25, 2024Jan 8, 2025Dec 24, 2025

Evaluation results

MethodLinks
MT-MH-SACImplementation=Reported in [43]2020.0388
Soft Modularization (Shallow)Network Depth=Shallow2020.0387
Soft Modularization (Deep)Network Depth=Deep2020.0386.7
MT-MH-SACImplementation=Internal implementation baseline2020.0385
MT-SACImplementation=Internal implementation baseline2020.0344
Mix-ExpertImplementation=Internal implementation baseline2020.0342.8
MT-SACImplementation=Reported in [43]2020.0339.5
GLiBRL2025.1225
Hard RoutingImplementation=Internal implementation baseline2020.0320.8
SDVT2025.1219
ECET2025.1218
TrMRL2025.1214